oneTaken

@PeterXiaoGuo @Spandan-Madan If it's necessary, I would update this tutorial to pytorch **0.4**. By the way, is the **index.html** transformed from a notebook?

I should comment earlier. I thought your code runs well, and I have it's due to my incorrect coding. There are some points during my debug phase: 1. your `p1...

Thanks for the question1 answer, i got it . I should follow the upddates. As for 2, have you got a not bad performance? I have some question about the...

Actually, I trained a keras model, which reproduced the paper result totally. But it's hard to understand the paper deeply, even though I got the result. So, I try to...

Emmm, I know you are familar to keras. I watched your respositories. Good job. But sadly, the keras code is not mine. So, I have to train with code myself....

Emm, I am trying to wrap the code into tensorboard. So I can compare with the keras training log, to have a more clear knowledge. By the way, I have...

Yeah, I am also use this repository. The weights says they were not updated. And there are gradients, so the graph can flow through the layers. So, there may be...

Will it have a sailent performance imporovement after removing this?

It seems that the training EM can be higher, I got 90% ever before. This is the experiment details in keras, before fine-tuning again: 1. Adam is better than Adadelta,...

- The custom loss function is different, we manually wrote a loss layer with mask. It seems that keras supports mask well. Besides, defines a new loss Variable, rather than...